{"adoption": {"forks": 4959, "observed_at": "2026-08-28T04:11:07.641294+00:00", "stars": 14756}, "canonical_url": "https://ross.abutalabs.com/products/reinforcement-learning-an-introduction", "card": {"archived": false, "artifact_type": "learning-resource", "description": "Python Implementation of Reinforcement Learning: An Introduction", "domain": ["reinforcement-learning", "artificial-intelligence", "machine-learning", "tutorials"], "enriched": true, "function": ["reinforcement-learning", "machine-learning", "data-visualization"], "health_score": 20, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "stable", "member_repos": ["ShangtongZhang/reinforcement-learning-an-introduction"], "name": "ShangtongZhang/reinforcement-learning-an-introduction", "platform": ["python", "cross-platform"], "pushed_at": "2024-08-09T01:09:15+00:00", "repo": "ShangtongZhang/reinforcement-learning-an-introduction", "stars": 14756, "tags": ["sutton-barto", "educational", "book-companion", "python-implementations", "figures"], "topics": ["reinforcement-learning", "artificial-intelligence"], "urls": [], "use_cases": ["study reinforcement learning alongside Sutton & Barto's book", "see working Python code for bandit and gridworld examples", "reproduce textbook figures like epsilon-greedy and UCB curves", "learn dynamic programming and Monte Carlo methods by example", "find reference implementations of TD learning algorithms"], "what_it_is": "Python implementations of the figures and examples from Sutton & Barto's 'Reinforcement Learning: An Introduction' (2nd Edition). It serves as a code companion to the textbook, replicating bandit algorithms, dynamic programming, Monte Carlo, and temporal-difference learning results.", "when_to_avoid": ["you need a production RL training library with GPU support", "you want modern deep RL algorithms like PPO or SAC", "you need exercise solutions for the book"], "when_to_choose": ["you are reading the Sutton & Barto textbook and want matching code", "you want simple, educational implementations rather than a heavy RL framework", "you need to reproduce the book's figures for study or teaching"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/reinforcement-learning-an-introduction", "repo": "ShangtongZhang/reinforcement-learning-an-introduction", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:11:07.641294+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:07:12.317247+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a03f0eb37a46497ce62b0e7e2118b89076127b1b54e1f8b23f514a2033e46654", "fetched_at": "2026-08-28T04:11:07.641294+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ShangtongZhang/reinforcement-learning-an-introduction"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:11:07.641294+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:07:12.317247+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a03f0eb37a46497ce62b0e7e2118b89076127b1b54e1f8b23f514a2033e46654", "fetched_at": "2026-08-28T04:11:07.641294+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ShangtongZhang/reinforcement-learning-an-introduction"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:07:12.317247+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a03f0eb37a46497ce62b0e7e2118b89076127b1b54e1f8b23f514a2033e46654", "fetched_at": "2026-08-28T04:11:07.641294+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ShangtongZhang/reinforcement-learning-an-introduction"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:11:07.641294+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:11:07.641294+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:11:07.641294+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:07:12.317247+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a03f0eb37a46497ce62b0e7e2118b89076127b1b54e1f8b23f514a2033e46654", "fetched_at": "2026-08-28T04:11:07.641294+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ShangtongZhang/reinforcement-learning-an-introduction"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:11:07.641294+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:11:07.641294+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:07:12.317247+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a03f0eb37a46497ce62b0e7e2118b89076127b1b54e1f8b23f514a2033e46654", "fetched_at": "2026-08-28T04:11:07.641294+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ShangtongZhang/reinforcement-learning-an-introduction"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:11:07.641294+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:11:07.641294+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:11:07.641294+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:07:12.317247+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a03f0eb37a46497ce62b0e7e2118b89076127b1b54e1f8b23f514a2033e46654", "fetched_at": "2026-08-28T04:11:07.641294+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ShangtongZhang/reinforcement-learning-an-introduction"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:11:07.641294+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:11:07.641294+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:07:12.317247+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a03f0eb37a46497ce62b0e7e2118b89076127b1b54e1f8b23f514a2033e46654", "fetched_at": "2026-08-28T04:11:07.641294+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ShangtongZhang/reinforcement-learning-an-introduction"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:07:12.317247+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a03f0eb37a46497ce62b0e7e2118b89076127b1b54e1f8b23f514a2033e46654", "fetched_at": "2026-08-28T04:11:07.641294+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ShangtongZhang/reinforcement-learning-an-introduction"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:07:12.317247+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a03f0eb37a46497ce62b0e7e2118b89076127b1b54e1f8b23f514a2033e46654", "fetched_at": "2026-08-28T04:11:07.641294+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ShangtongZhang/reinforcement-learning-an-introduction"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:07:12.317247+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a03f0eb37a46497ce62b0e7e2118b89076127b1b54e1f8b23f514a2033e46654", "fetched_at": "2026-08-28T04:11:07.641294+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ShangtongZhang/reinforcement-learning-an-introduction"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3641, "days_push": 755, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 32, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}